yt_dlp/extractor/mwave.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     int_or_none,
   5     parse_duration,
   6 )
   7
   8
   9 class MwaveIE(InfoExtractor):
  10     _VALID_URL = r'https?://mwave\.interest\.me/(?:[^/]+/)?mnettv/videodetail\.m\?searchVideoDetailVO\.clip_id=(?P<id>[0-9]+)'
  11     _URL_TEMPLATE = 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=%s'
  12     _TESTS = [{
  13         'url': 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=168859',
  14         # md5 is unstable
  15         'info_dict': {
  16             'id': '168859',
  17             'ext': 'flv',
  18             'title': '[M COUNTDOWN] SISTAR - SHAKE IT',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20             'uploader': 'M COUNTDOWN',
  21             'duration': 206,
  22             'view_count': int,
  23         }
  24     }, {
  25         'url': 'http://mwave.interest.me/en/mnettv/videodetail.m?searchVideoDetailVO.clip_id=176199',
  26         'only_matching': True,
  27     }]
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         vod_info = self._download_json(
  33             'http://mwave.interest.me/onair/vod_info.m?vodtype=CL&sectorid=&endinfo=Y&id=%s' % video_id,
  34             video_id, 'Download vod JSON')
  35
  36         formats = []
  37         for num, cdn_info in enumerate(vod_info['cdn']):
  38             stream_url = cdn_info.get('url')
  39             if not stream_url:
  40                 continue
  41             stream_name = cdn_info.get('name') or compat_str(num)
  42             f4m_stream = self._download_json(
  43                 stream_url, video_id,
  44                 'Download %s stream JSON' % stream_name)
  45             f4m_url = f4m_stream.get('fileurl')
  46             if not f4m_url:
  47                 continue
  48             formats.extend(
  49                 self._extract_f4m_formats(f4m_url + '&hdcore=3.0.3', video_id, f4m_id=stream_name))
  50         self._sort_formats(formats)
  51
  52         return {
  53             'id': video_id,
  54             'title': vod_info['title'],
  55             'thumbnail': vod_info.get('cover'),
  56             'uploader': vod_info.get('program_title'),
  57             'duration': parse_duration(vod_info.get('time')),
  58             'view_count': int_or_none(vod_info.get('hit')),
  59             'formats': formats,
  60         }
  61
  62
  63 class MwaveMeetGreetIE(InfoExtractor):
  64     _VALID_URL = r'https?://mwave\.interest\.me/(?:[^/]+/)?meetgreet/view/(?P<id>\d+)'
  65     _TESTS = [{
  66         'url': 'http://mwave.interest.me/meetgreet/view/256',
  67         'info_dict': {
  68             'id': '173294',
  69             'ext': 'flv',
  70             'title': '[MEET&GREET] Park BoRam',
  71             'thumbnail': r're:^https?://.*\.jpg$',
  72             'uploader': 'Mwave',
  73             'duration': 3634,
  74             'view_count': int,
  75         }
  76     }, {
  77         'url': 'http://mwave.interest.me/en/meetgreet/view/256',
  78         'only_matching': True,
  79     }]
  80
  81     def _real_extract(self, url):
  82         video_id = self._match_id(url)
  83         webpage = self._download_webpage(url, video_id)
  84         clip_id = self._html_search_regex(
  85             r'<iframe[^>]+src="/mnettv/ifr_clip\.m\?searchVideoDetailVO\.clip_id=(\d+)',
  86             webpage, 'clip ID')
  87         clip_url = MwaveIE._URL_TEMPLATE % clip_id
  88         return self.url_result(clip_url, 'Mwave', clip_id)